Prefeitura SP São Paulo: Caixa Postal

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since annotations are minimal (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description carries the burden. It clearly explains the behavior: it opens a login link, accepts a token for session login, and notes the permanent option via config. It also mentions that adding to config leads to a non-expiring connection, which is essential behavioral context. No contradictions with annotations are present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the target audience and main action, then gives a step-by-step in two sentences. It is compact, informative, and every sentence adds value—no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one optional parameter and no output schema, the description is quite complete: it covers the login flow, token usage, and permanent config option. It could mention what happens on success/failure (e.g., response format), but that's not critical given the simplicity. Without an output schema, a brief note on return value would be helpful, but the description is adequate for an agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one optional parameter 'token' with no description, and the description explicitly explains it: 'token: "<jwt>"' for session login. It adds meaning beyond the schema by specifying the format (JWT) and usage context. Since coverage is 0% but the param is fully explained, a 4 is appropriate; the only missing detail is explicit format (e.g., no regex or examples), but it's clear enough.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: it authenticates IDE agents to MCP.AI by providing a login link and accepting an access token. It distinguishes from siblings by specifying the exact workflow (browser login, token paste, config header) and mentions alternatives like using the server config.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit guidance on when and how to use it: 'call with { token: "<jwt>" } after the user pastes, or with no args to get the link.' It also provides a preferred alternative (adding to config) and explains the session-only vs. permanent distinction, which is clear usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, indicating a safe read operation. The description goes beyond annotations by specifying the exact output structure in two scenarios (all connected vs. missing credentials), including the presence of 'authenticated' and 'pending' fields and the connect_url. This adds meaningful behavioral detail with no contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose, then adds conditional detail. Every sentence is informative; there is no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters, benign annotations, and no output schema, the description provides sufficient context by detailing the response in both success and failure scenarios. It fully covers what an agent needs to know to use the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so schema coverage is trivially 100%. The baseline for a no-parameter tool is 4, and the description adds value by explaining the tool's behavior without needing to describe parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: returns connection status and URLs. It specifies the output variations based on connection state, which distinguishes it from siblings like 'authenticate' that likely perform authentication rather than check status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when the tool is useful—checking connection status—and explains the conditional behavior when credentials are missing. However, it does not explicitly contrast with the sibling 'authenticate' or state when one should be preferred, so it misses a direct usage guideline.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses key behavioral traits beyond annotations: invoke runs one-off without adding to toolkit, requires connect/checkout links for auth/payment, writes require owner/admin, and search/describe flag installation status. This adds substantial context not present in the minimal annotations (readOnlyHint=false, openWorldHint=true), helping the agent anticipate side effects and prerequisites.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is lengthy but well-structured, starting with purpose, then core flow, special invoke behavior, install vs invoke preference, permissions, and prompt library. It front-loads key information and packs a lot of useful guidance without excessive filler. Slightly verbose due to the sheer scope, but every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (23 params, no output schema, rich annotations), the description is remarkably complete. It covers all major actions, edge cases (auth/payment links), permission requirements, installed-state flags, and the separate prompt library functionality. It gives an agent enough situational context to handle diverse use cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 23 parameters and 0% schema description coverage, the description carries the burden. It explains the action-dependent usage (e.g., search uses query, describe/invoke use mcp_id/tool_id), but does not explicitly enumerate each parameter or clarify the conditions for optional ones. It provides enough context to infer common flows, but not comprehensive parameter semantics for all 23 fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's role: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It names specific actions (search, describe, invoke, install) and distinguishes itself as the central hub for discovering and executing MCPs, which differentiates it from sibling tools like authenticate or connect.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use guidance: 'Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use,' and explains the core flow (search → describe → invoke). It also notes permission requirements for writes and mentions alternatives like report_bug and request_mcp when nothing fits. These instructions help an agent choose the right action and tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this as read-only, idempotent, and non-destructive, which covers the safety profile. The description further clarifies that the data is not confidential and that LGPD responsibilities fall on the customer. It does not describe response format or pagination, but for a simple read operation, this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence containing extra context about hosting, payment, and legal compliance. While not verbose, it includes some tangential information that could be moved elsewhere, and it omits parameter details, so the structure is imbalanced for a 4-parameter tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the service type, payment model, and data governance angle, but it fails to explain the required credentials (pkcs12_cert, pkcs12_pass) or the optional flags (ignora_lidas, ignora_nao_lidas). There is no mention of the output schema or how the query results are returned, which is important for a paid query tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides no descriptions for any of the four parameters. Required parameters pkcs12_cert and pkcs12_pass are self-explanatory by name, but the optional 'ignora_lidas' and 'ignora_nao_lidas' are completely ambiguous. The description only mentions payment and data governance, not parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The tool name and description clearly indicate it is for querying Caixa Postal information from São Paulo's city hall. The description specifies the official source and that it provides the same data available to citizens. It is distinct from the sibling tools, which are general platform utilities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions that this is a paid per-query service with prepaid credits and does not require platform credentials, which are useful prerequisites. However, it does not name any alternative tools or specify when to use this versus another method, though the sibling list contains no similar query tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations indicate idempotentHint=true and destructiveHint=false, so the description does not contradict them. The description adds context that the tool is for reporting and that it expects a conversation array for reproduction. It doesn't detail side effects, but idempotency and non-destructive nature are already covered by annotations, which lowers the bar. The description adds the reproduction guidance, which is useful.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, two sentences, and front-loaded with the main purpose. Every word earns its place, providing the essential actionable instruction without unnecessary fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is straightforward (reporting feedback) with three parameters and no output schema. The description is sufficient for the agent to understand what to do, especially with the reproduction hint. It lacks details on response format or side effects, but given the low complexity and annotation coverage, it is fairly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 0%, so the description must compensate. The description explains the 'conversation' parameter partially by saying to include it, but it does not elaborate on 'context' or 'message' beyond the schema's basic definitions. The description adds a bit of meaning by specifying that conversation should contain recent messages, but it lacks detail on the other parameters. Baseline is 3 due to low coverage, but it does not fully compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Report a bug, missing feature, or send feedback.' It uses a specific verb ('Report') and identifies the resource (bug/feature/feedback). It distinguishes itself from siblings like 'authenticate' or 'connect' by focusing on bug reporting and feedback.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on what to include: 'Include the conversation array with recent messages for reproduction.' This tells the agent when and how to use the tool (when reporting an issue) and what supplementary information is needed. However, it does not explicitly state when not to use it or mention alternatives, but the context is clear enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds scope ('current platform and adapter versions') but does not disclose return format or any additional runtime behavior, which is acceptable given the annotation support.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler. Every word contributes to identifying the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-parameter version information tool with strong annotations and no output schema, this description is sufficient. It fully states what the tool reports and has no complex edge cases needing explanation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the parameter-semantics baseline is 4. The description correctly adds no irrelevant parameter details, and schema coverage is already complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific action, 'show', and clearly identifies the resource as 'current MCP platform and adapter versions,' making the tool's function unambiguous. It does not explicitly distinguish itself from siblings such as toolkit_info or marketplace, so it falls just short of the highest rating.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance about when to use this tool versus alternatives, or when not to use it. With sibling tools like toolkit_info and marketplace, an agent would have to infer the appropriate context without explicit direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds value by specifying exactly what state is returned (MCPs, statuses, accounts, catalog tool counts), which is useful behavioral context beyond the annotations. It does not mention potential latency or permissions, but for a read-only info tool this is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Exactly one sentence that is front-loaded with the main purpose and provides detailed examples of the return contents without unnecessary words. Every phrase contributes to understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only informational tool with no parameters and no output schema, the description is complete. It outlines the key result categories, which is exactly what an agent needs to set expectations for the returned state.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4 per the rubric. The description does not add parameter details because none are needed and the schema trivially covers all parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Returns the current toolkit state' with specific details on the return content (installed MCPs, connection status, accounts, catalog tool counts). The verb 'Returns' plus the precise object distinguishes it from siblings like 'show_version' or 'marketplace'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use (to get state info) but does not explicitly mention alternatives or exclusions. It does not contrast with similar tools like 'show_version', so usage guidance relies solely on the clarity of purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.